V
主页
Learning Dynamics from Bilinear Observations by Sarah Dean
发布人
Learning Dynamics from Bilinear Observations by Sarah Dean July 02, 2024 Bio: Prof. Sarah Dean, Cornell University Abstract: When machine learning models are deployed, for example in recommender systems, they can affect the environment in which they operate. Such effects arise when decisions impact individuals, and these effects can cause issues like polarization and radicalization. I will discuss models of impact and their implications in the context of recommendation systems. Then I will turn to the question of learning such models from data. Several challenges arise due to temporal dependence and inherent nonlinearity in the observations. This talk will draw on recent work on preference dynamics and harm in personalized recommendations, as well as a current project on system identification with bilinear observations.
打开封面
下载高清视频
观看高清视频
视频下载器
Towards Gain-optimal ISS Controllers for Finite State Systems by Antoine Girard
Planning and Discussion Session
Aligning Robot and Human Representations by Andreea Bobu
Learning-based Planning and Control: Opportunities and Challenges by J. How
IFAC Industry Connect: Automation & Control: An Integral Part of Process...
Dynamics and Control of Differential Learning by Stefano Soatto (UC Berkeley)
Learning Certifiably Safe Control for Large-scale Autonomous Systems by C Fan
Cheating with Neural Networks by Zico Kolter
Machine Learning: Bane Or Boon For Control? by Miroslav Krstic @CDC2023
Understanding the Utility of Haptic Feedback in Telerobotic Devices by J Brown
Efficient Reinforcement Learning When Data is Costly by Emma Brunskill
Bridging the Gap Between Planning and Control: A Cascaded MPC Approach by J Z Lu
New Complexities in New Aviation: UTM, UAM, and RAM by Raja Sengupta
Enabling a Responsive Grid with Distributed Load Control and Optimization
A Practitioner’s Perspective by Manfred Morari
Direct Adaptive Learning of the LQR by Florian Dörfler
The Shades of Reinforcement Learning by John Tsitsiklis
Embedded Convex Optimization for Control by Stephen Boyd
Feedback in Wafer Scanners: Use the Unstable by Marcel Heertjes @ CCTA 2021
Driving the Elephant through the Landscape of Deep Networks Stefano Soatto
Frontiers of Autonomous Space Systems by Giusy Falcone
How Much Uncertainty Can the Feedback Mechanism Deal With? by Lei Guo @IFAC2014
Optimizing Intended Cost Functions by Anca Dragan
Learning for Safety-Critical Control in Dynamical Systems by Yisong Yue
Dual Control Revisited by Anders Rantzer @ CDC 2024
Infusing Physics and Structure into Machine Learning by Anima Anandkumar
Towards Collective Artificial Intelligence by Radhika Nagpal @ IROS2022
Mathematics of Deep Learning by René Vidal @ ACC2019
Bionic Learning Network – Inspired by Nature by Heinrich Frontzek @IFAC2014
The Joy of Exploring the Emerging Dynamics of Integrated Systems by Jing Sun
Learning and Control for Safety, Efficiency, and Resiliency of Embodied AI
The Impact of Model-Based Design on Controls: Today & in the Future by J Little
Physics-Guided Data-Driven Modeling for Control in Additive Manufacturing
Regret-Optimal Control by Babak Hassibi
Safe and Efficient Exploration in Reinforcement Learning by Andreas Krause
Prediction, Estimation, and Control Of Connected & Autonomous Vehicles by J. Sun
Pioneering the Future Aerospace by Charles Champion and Grazia Vittadini
Resilience in State Estimation and System Identification by Laurent Bako
“Control Meets Neuroscience” Panel Discussion @ IFAC 2020
Livestream of the 2nd L4DC conference (Day 2)